Computer Vision Model Selection, Architecture Design & Training Strategy
Design Production-Ready Computer Vision Models Fast
What You Can Do
You'll gain structured workflows to architect computer vision models from scratch, optimize training pipelines for your hardware constraints, and debug common CV issues like vanishing gradients or poor data augmentation. This skill walks you through model selection (CNN, Vision Transformers, YOLO variants), training strategy design, and performance profiling — turning research papers into production-ready systems.
Features
Evaluate CNNs, Vision Transformers, EfficientNets, and specialized architectures (YOLO, Mask R-CNN) against your accuracy-latency tradeoffs
Profile data loaders, batch sizes, learning rates, and augmentation strategies to maximize GPU utilization and convergence speed
Diagnose vanishing gradients, underfitting, overfitting, and data quality issues with step-by-step decision trees and remediation strategies
Decision tree for choosing PyTorch vs TensorFlow vs JAX based on team expertise, deployment target, and research needs
Pre-built strategies for image classification, object detection, semantic segmentation, and multi-task CV workflows
Evaluate fine-tuning vs feature extraction vs domain adaptation based on dataset size and task similarity
Measure inference latency, memory footprint, accuracy on edge devices, and identify optimization bottlenecks
Verify model quantization, ONNX export, batch inference setup, and deployment target compatibility
Example Output
Example 1: Model Selection for Real-Time Object Detection
Input: "I need to detect cars in 1080p video at 30 FPS on an NVIDIA Jetson. Dataset is 50K labeled images."
Output:
Recommended: YOLOv8-nano (PyTorch)
- Inference: ~15ms per frame on Jetson (achieves 67 FPS target)
- Accuracy: mAP 0.37 (sufficient for tracking)
- Memory: 6.5MB (fits on-device)
- Alt: TensorFlow Lite MobileNet-SSD if iOS deployment needed
Training Strategy:
1. Start with pretrained YOLOv8-nano on COCO
2. Augmentation: Random hue/saturation shifts, horizontal flips, mosaic (for varied object scales)
3. Batch size: 64 on V100 (adjust if OOM)
4. Learning rate: 0.01 → 0.001 (cosine annealing over 100 epochs)
5. Validation: Split 10% of data, measure mAP every 10 epochs
Example 2: Debugging Vanishing Gradients
Symptom: Loss plateaus after 5 epochs, weights don't update.
Diagnosis Tree:
✓ Check gradient magnitude at each layer → gradients < 1e-7 in early layers?
✓ Add batch norm before activation functions
✓ Reduce learning rate (0.01 → 0.001) or use warm-up schedule
✓ Verify data normalization (images scaled to [-1, 1] or [0, 1]?)
✓ Switch activation: ReLU → Leaky ReLU for deeper networks
✓ Add skip connections (ResNet-style) if depth > 50 layers
Result: Adding batch norm + skip connections → loss resumes descent
What's Included
- SKILL.md: Complete CV model selection and training workflows with decision trees, validation checklists, and debugging playbooks
- Architecture comparison template: Side-by-side specs (latency, accuracy, memory) for 15+ model families
- Training configuration checklist: Data loading, augmentation, optimization, and hardware setup verification
- Debugging decision tree: Common CV failure modes and remediation strategies
- Framework selection guide: PyTorch vs TensorFlow vs JAX comparison matrix
- Data augmentation recipes: 8+ strategies (class-balanced, geometric, photometric, mixup variants)
- Performance profiling script template: Measure inference time and memory on target hardware
Who It's For
- ML Engineers building production computer vision systems from prototype to deployment
- Computer Vision Specialists designing custom architectures for novel applications
- Data Scientists scaling image classification, detection, or segmentation projects
- AI Product Managers evaluating model feasibility and resource requirements for new features
- Research Scientists transitioning academic models into robust, reproducible training pipelines
Best For
- Model architecture selection for new image classification, detection, or segmentation projects
- Training pipeline optimization to maximize accuracy within latency/memory constraints
- Debugging convergence issues when loss plateaus or gradients vanish
- Framework and library decisions when choosing PyTorch, TensorFlow, or other stacks
- Data augmentation strategy design to improve model robustness with limited data
- Edge device deployment planning for Jetson, mobile, or browser-based inference
- Transfer learning evaluations to decide between fine-tuning pretrained models vs training from scratch
You might also like
Query your local Screenpipe instance to retrieve screen recordings, audio transcriptions, UI element accessibility trees, keyboard/mouse input logs, and productivity analytics. You can search by keywords, filter by content type (audio, OCR, accessibility, input), set time ranges, and extract structured data about your applications, meetings, and work sessions without sending data to external servers.
by az9713
You can conduct comprehensive slope stability analyses that integrate site characterization, soil/rock properties, and quantitative calculations to evaluate both simple and complex slope geometries. The framework helps you identify critical failure mechanisms, calculate safety factors, assess groundwater and seismic effects, and develop technically defensible remediation recommendations suitable for permitting, design decisions, and stakeholder communication.
by az9713
You can systematically design test cases for any feature or system by analyzing requirements or code to extract test parameters, values, and business constraints. The skill generates a PICT model, executes pairwise testing logic to minimize test case count while maximizing coverage, and delivers a formatted test matrix with expected results—reducing manual test design effort while ensuring comprehensive scenario coverage.
by az9713
This skill deconstructs your writing samples to identify the specific patterns, personality markers, emotional range, language quirks, and formatting habits that make your voice uniquely yours. You'll receive a detailed voice DNA profile that includes your core communication style, signature phrases, emotional tone, formality level, and what you actively avoid—creating a blueprint that AI systems can use to replicate your authentic voice consistently across projects, platforms, and content types.
by az9713
You can decompose complex timber structures into analyzable load paths, trace forces from applied loads through members to supports, and calculate governing demands for each structural element. This skill helps you identify critical design points, apply appropriate load factors and duration adjustments, and create defensible design documentation that satisfies code officials and peer reviewers.
by az9713
You can compare building materials across embodied carbon, water usage, recyclability, supply chain impacts, and lifecycle costs—all grounded in industry standards like EN 15804 and ISO 14040/44. This skill transforms material selection from intuition-based guessing into data-driven specification, producing analysis outputs ready for client presentations, value engineering discussions, and regulatory compliance documentation.
by az9713
You can audit BIM models across five critical domains: geometric accuracy and LOD consistency, information requirements and metadata, coordinate systems and project setup, element naming and classification standards, and documentation completeness. This skill generates detailed compliance reports that identify every gap and provide specific remediation guidance, enabling you to enforce consistent standards across projects, reduce rework, and ensure models are ready for handoff to downstream disciplines or coordination workflows.
by az9713
You can accelerate HVAC design workflows by inputting building parameters—envelope characteristics, occupancy data, climate conditions, and existing systems—and receiving calculated heating/cooling loads, equipment sizing recommendations, and zone-by-zone analysis. Claude organizes complex building data into actionable design parameters and specification summaries for client review, permit submission, and professional validation against ASHRAE and ACCA standards.
by az9713